A Task-Adaptive Parameter Transformation Scheme for Model-Agnostic-Meta-Learning-Based Few-Shot Animal Sound Classification

Jaeuk Moon, Eunbeen Kim, Junha Hwang, Eenjun Hwang

    Research output: Contribution to journalArticlepeer-review

    1 Citation (Scopus)

    Abstract

    Deep learning models that require vast amounts of training data struggle to achieve good animal sound classification (ASC) performance. Among recent few-shot ASC methods to address the data shortage problem regarding animals that are difficult to observe, model-agnostic meta-learning (MAML) has shown new possibilities by encoding common prior knowledge derived from different tasks into the model parameter initialization of target tasks. However, when the knowledge on animal sounds is difficult to generalize due to its diversity, MAML exhibits poor ASC performance due to the static initialization setting. In this paper, we propose a novel task-adaptive parameter transformation scheme called few-shot ASC. TAPT generates transformation variables while learning common knowledge and uses the variables to make parameters specific to the target task. Owing to this transformation, TAPT can reduce overfitting and enhance adaptability, training speed, and performance in heterogeneous tasks compared to MAML. In experiments on two public datasets on the same backbone network, we show that TAPT outperforms the existing few-shot ASC schemes in terms of classification accuracy, and in particular a performance improvement of 20.32% compared to the state-of-the-art scheme. In addition, we show that TAPT is robust to hyperparameters and efficient for training.

    Original languageEnglish
    Article number1025
    JournalApplied Sciences (Switzerland)
    Volume14
    Issue number3
    DOIs
    Publication statusPublished - 2024 Feb

    Bibliographical note

    Publisher Copyright:
    © 2024 by the authors.

    Keywords

    • MAML
    • animal sound classification
    • bioacoustics classification
    • deep learning
    • few-shot learning
    • meta-learning

    ASJC Scopus subject areas

    • General Materials Science
    • Instrumentation
    • General Engineering
    • Process Chemistry and Technology
    • Computer Science Applications
    • Fluid Flow and Transfer Processes

    Fingerprint

    Dive into the research topics of 'A Task-Adaptive Parameter Transformation Scheme for Model-Agnostic-Meta-Learning-Based Few-Shot Animal Sound Classification'. Together they form a unique fingerprint.

    Cite this